The 4e PHB comments (p 259) that in a skill challenge "You can use a wide variety of skills, from Acrobatics and Athletics to
Nature and Stealth. You might also use combat powers . . ." The DMG says (p 72) "The difference between a combat challenge and a skill challenge isn’t the presence or absence of physical risk, nor the presence or absence of attack rolls and damage rolls and power use", and goes on to say (p 74) that "[c]haracters might have access to utility powers or rituals that can help them. These might allow special uses of skills, perhaps with a bonus. Rituals in particular might grant an automatic success or remove failures from the running total." The DMG2 is the most elaborate on this (p 86), suggesting that "[c]haracter can use powers and sometimes rituals in the midst of skill challenge . . . a good rule of thumb is to treat those . . . as if they were secondary skills in the challenge [ie that cancel a failure, grant a bonus to a different check, allow a reroll, or open up the use of a new skill, as per p 85] . . . A character who performs a relevant rituak or uses a daily power deserves to notch at lesat 1 success toward the party's goal."
At least as I read this, there are two things going on (and from here I'm focused only on powers, though I'm happy to talk about rituals too if you're interested). One is that 4e capabilities have a clear "cost structure" as resources - encounter powers are low-cost resources, and expending them generally generates a modest return (the seondary skill check outcomes mentioned); daily powers are higher-cost resources, and expending them therefore generally generates a higher return (the auto-success outcome mentioned).
The other thing turns on the facts that (a) a skill challenge is all about
making a check that is grounded in the existing ficitonal positioning, and changes that whether it succeeds or fails (DMG p 74; DMG 2 p 83); and (b) the main connection between a power and the fiction is the power's keywords and effects.
So to use a power to generate an effect appropriate to its "cost" as a player resource, the player has to actually declare a move in the fiction that expresses the (keyword and effect) mediated fiction of the power. Two examples of what I have in mind:
a sorcerer uses Spark Form to generate an arc of lightning between his staff and his dagger to help intimidate a bear - keyword
lightning; and
a wizard uses Charm of the Dark Dream - a possession daily - to try and read the mind of a guard and learn a password - keyword
charm and effects
dominate, attacking character is removed from play (ie in the fiction, the mage disappears and possesses the target).
The first RPG I know to use a system a bit like this is Maelstrom Storytelling (1997), which uses a uniform scene-resolution mechanic based on dice pools (either opposed or vs a difficulty), and allows players to "burn" descriptors (ie use them up for the session) to add bonus dice to the pool, or to generate "sub-scenes" that they can try and win even if the group loses the overall scene. Because 4e has a robust and uniform-across-players resource economy, it is easy to adapt the same sort of thing into skill challenges, which is - as I read it - what the DMG2 has in mind.
In a system in which players don't have these uniform suites of resources, and don't use keywords to provide clear but also flexible anchors to the fiction, this sort of thing (in my view) becomes much harder to adjudicate.